© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64852
    Prev
    Next
    INDEX
    Explanations

    steel

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subtropical
    0.38
    ★★★
    0.38
     β
    0.37
     Burj
    0.36
    垡
    0.35
     lounge
    0.35
     Pol
    0.34
    রাশ
    0.34
    зи
    0.34
    られない
    0.34
    POSITIVE LOGITS
     cal
    1.26
     steel
    1.12
     Cal
    1.09
    Cal
    1.06
     Steel
    0.99
    steel
    0.98
    Steel
    0.97
    钢
    0.95
    cal
    0.93
     STEEL
    0.93
    Activations Density 0.001%

    No Known Activations